concept high dimension in category deep learning

appears as: higher dimensions, high dimensions
Math and Architectures of Deep Learning

This is an excerpt from Manning's book Math and Architectures of Deep Learning.

The geometric view holds in higher dimensions too. In general, a n-dimensional input vector  is mapped to a m-dimensional output vector (usually m < n) in such a way that the problem becomes much simpler in the output space. An example with 3D feature space is shown in Figure 1.3.

This holds true in general, and for higher dimensions too. This is the mental picture to have with respect to independent versus non-independent point distributions.